Article
Chemistry, Analytical
Nika Brili, Mirko Ficko, Simon Klancnik
Summary: This study presents an automatic Tool Condition Monitoring (TCM) system that classifies tool wear into four categories and achieves over 96% accuracy using an Infrared (IR) camera and Convolutional Neural Network Inception V3. The best time for image acquisition is 6-12 seconds after the cut is finished.
Article
Materials Science, Paper & Wood
Weihang Dong, Xiaolei Guo, Yong Hu, Jinxin Wang, Guangjun Tian
Summary: This paper proposes an effective method based on DWT and GA-BP neural network to monitor tool wear conditions under different milling parameters, improving the processing quality of wood plastic composite furniture and reducing energy consumption.
Article
Computer Science, Information Systems
Jun Wang, Tingting Zhou
Summary: This paper proposes a model and data fusion method based on particle filter algorithm for monitoring cutting tool wear. Experimental results show that the fusion method has lower error and is closer to 1 in terms of coefficient of determination, demonstrating its feasibility and superiority.
Article
Thermodynamics
Liqiang Wang, Xiao Li, Bo Shi, Munyaradzi Munochiveyi
Summary: This paper proposes an experimental scheme to monitor tool wear state by extracting vibration signals. Time domain and frequency domain analyses are conducted, and wavelet packet decomposition is applied for further analysis. The characteristic frequency bands and energy percentages closely related to tool wear are identified.
ADVANCES IN MECHANICAL ENGINEERING
(2022)
Article
Chemistry, Physical
Maciej Tabaszewski, Pawel Twardowski, Martyna Wiciak-Pikula, Natalia Znojkiewicz, Agata Felusiak-Czyryca, Jakub Czyiycki
Summary: This paper compares different intelligent system methods to identify tool wear and explores the application of machine learning in improving the quality of manufacturing industries. The results show that machine learning methods based on vibration acceleration signals can effectively predict the wear condition of tools.
Article
Multidisciplinary Sciences
Kejia Zhuang, Zhenchuan Shi, Yaobing Sun, Zhongmei Gao, Lei Wang
Summary: This study presents a method based on Digital Twin (DT) to achieve high precision in monitoring and predicting tool wear. The framework of the cutting tool system DT is designed, key enabling technologies are elaborated, and a case study of the turning process is presented to verify the feasibility of the framework.
Article
Engineering, Mechanical
Sebastian Bombinski, Joanna Kossakowska, Krzysztof Jemielniak
Summary: Comparing waveforms of cutting force sensor signals in hierarchical time windows allows for successful detection of accelerated tool wear (ATW) and prevention of catastrophic tool failure (CTF).
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Multidisciplinary
Jawad Mahmood, Ghulam-E Mustafa, Muhammad Ali
Summary: This study focuses on machining operations using milling, drilling, and turning tools. Two models were developed to address tool wear, and various techniques were applied to improve the models' performance and prevent overfitting.
Article
Automation & Control Systems
Meng Lip Lim, Mohd Naqib Derani, Mani Maran Ratnam, Ahmad Razlan Yusoff
Summary: This study aims to develop deep learning regression models to predict tool wear state using features extracted from 2-D images of the workpiece surface profile. The prediction accuracy of two models, convolutional neural network (CNN) and deep neural network (DNN), were compared. The results show that the CNN model provides more reliable prediction of tool wear state.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Jian Duan, Jie Duan, Hongdi Zhou, Xiaobin Zhan, Tianxiang Li, Tielin Shi
Summary: A novel deep learning model, MFB-DCNN, is proposed in this paper to handle machining big data and monitor tool condition. Experimental results show that the model has outstanding generalizability and higher prediction performance, and it can remedy the absence of complicated feature engineering.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Mathematics, Applied
Zhiguo Zhang, Mark A. Kon
Summary: This study introduces a method to implement quantum wavelet transforms by introducing new inner products and norms and converting wavelet transform algorithms into matrix forms for quantum computation. The results show that infinite matrix operators can be converted into finite forms through singular value decompositions, enabling the implementation of standard wavelet transforms.
APPLIED MATHEMATICS AND COMPUTATION
(2022)
Article
Automation & Control Systems
A. Al-Azmi, Amin Al-Habaibeh, Jabbar Abbas
Summary: This paper develops an effective sensor fusion model for detecting tool wear in turning processes. The fusion of sensor data, novelty detection algorithm, and LVQ neural networks is used for detecting and predicting tool wear. The ASPS approach is employed to select appropriate sensors and signal processing methods for the condition monitoring system design. Experimental results demonstrate the efficacy of the proposed approach in monitoring tool wear.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Engineering, Mechanical
Maohua Xiao, Wei Zhang, Kai Wen, Yue Zhu, Yilidaer Yiliyasi
Summary: In this study, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which accurately distinguishes different states of the bearing through visualization of energy features using K-Means clustering. A fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify bearing faults with an accuracy exceeding 95% and certain anti-interference capability. Two experiments demonstrate the effectiveness of the model in fault diagnosis.
CHINESE JOURNAL OF MECHANICAL ENGINEERING
(2021)
Article
Automation & Control Systems
Jing Bi, Haitao Yuan, Jiahui Zhai, MengChu Zhou, H. Vincent Poor
Summary: This work proposes an improved self-adaptive bat algorithm with genetic operations (SBAGO) that combines genetic algorithm (GA) and bat algorithm (BA) in a highly integrated way. SBAGO utilizes the search information of BA to perform GA's genetic operations, resulting in improved search performance. Experimental results show that SBAGO outperforms other algorithms in various metrics.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Chemistry, Analytical
Juan Luis Ferrando Chacon, Telmo Fernandez de Barrena, Ander Garcia, Mikel Saez de Buruaga, Xabier Badiola, Javier Vicente
Summary: There is an increasing trend in the industry towards real-time monitoring of critical aspects like tool wear to reduce costs and scrap in machining processes. Machine learning models based on tool wear data are becoming popular as they simplify the development of physical models. While acoustic emission (AE) technique is widely used for real-time monitoring of industrial assets like cutting tools, the interpretation and processing of AE signals is complex.
Article
Automation & Control Systems
Ritam Upadhyay, Abhishek Asi, Pravanjan Nayak, Nidhi Prasad, Debasish Mishra, Surjya K. Pal
Summary: Artificial intelligence is revolutionizing the manufacturing industry by introducing flexible robots that collaborate with humans to enhance productivity. This article presents an AI-based solution for real-time grasping of cuboid- and cylindrical-shaped objects without prior knowledge of their 3D structure, achieving high accuracy.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Thermodynamics
Omkar Mypati, Tariq Anwaar, Desham Mitra, Surjya Kanta Pal, Prakash Srirangam
Summary: This study describes the sustainability of busbars in lithium-ion batteries and investigates the changes in process parameters of friction stir welded (FSW) samples at different electrical conductivity levels. The results show that the electrical conductivity varies with the formation of intermetallic compounds and changes in grain size at the Al-Cu joint.
APPLIED THERMAL ENGINEERING
(2023)
Article
Materials Science, Multidisciplinary
Matruprasad Rout, Surjya K. Pal, Shiv Brat Singh
Summary: In this study, the microstructure evolution of austenitic stainless steel after deformation at elevated temperatures was investigated through thermo-mechanical processing. The results showed that at temperatures of 900 degrees C and 1000 degrees C, the microstructures of samples held for 2 seconds consisted of deformed grains, while the sample held at 1100 degrees C showed nearly complete recrystallization. The increase in holding time resulted in a decrease in low angle boundaries and an increase in high angle grain boundaries at all three temperatures.
MATERIALS CHEMISTRY AND PHYSICS
(2023)
Article
Automation & Control Systems
Riya Tapwal, Pallav Kumar Deb, Sudip Misra, Surjya Kanta Pal
Summary: Storing data from IIoT sensors in blockchain for monitoring applications can cause management issues like bloating. This study focuses on generating traces using an ARIMA model and storing only metadata, resulting in reduced delay and managed data. Size of traces for storage on the store is determined by considering principal parameters and S&G blocks are generated accordingly. Feasibility of S&G is demonstrated with errors and regret in the range of 0.07-0.10 and 0.20-0.25, respectively, using the appropriate ARIMA model.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Materials Science, Multidisciplinary
Rishabh Swarnkar, Souvik Karmakar, Surjya K. Pal
Summary: This article proposes a novel friction stir backward extrusion (FSBE) process for the fabrication of bimetallic tubular components. The process enables uniform cladding and void-free bonding between different sets of materials through diffusion and frictional heat. Intermetallic compounds (IMCs) were confirmed at the interface through energy dispersive spectroscopy (EDS) and X-ray diffraction (XRD) analyses. The strong metallurgical bonding between the substrate and cladding materials was verified through a flattening test. This process opens up new opportunities for applications in electrical, structural, lightweight, and corrosion-resistant fields.
MATERIALS TODAY COMMUNICATIONS
(2023)
Review
Computer Science, Artificial Intelligence
Omkar Mypati, Avishek Mukherjee, Debasish Mishra, Surjya Kanta Pal, Partha Pratim Chakrabarti, Arpan Pal
Summary: This article provides a detailed survey of AI algorithms and their applications in manufacturing, including casting, forming, machining, welding, additive manufacturing, and supply chain management. It discusses the evolution of processes, automation using signal and image processing, and the application of ML and AI algorithms. The article also reviews the development of robotics and cloud-based technologies and highlights the benefits of AI in manufacturing. It concludes by discussing manufacturing use cases and the need for cognitive skills in manufacturing for future research.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Engineering, Chemical
Soumya Sangita Nayak, Md Perwej Iqbal, Rahul Jain, Surjya K. Pal, Prakash Srirangam
Summary: This study aims to model temperature distribution in friction stir welding (FSW) using various backing plates and polygonal pin profiles. The experimental results show the importance of temperature on the grain size and tensile strength of the materials. However, determining the temperature at each point of the weld is difficult and expensive in experiments. Therefore, simulations are performed to accomplish the objective. The 3-D transient multiphysics model developed for FSW combines multiple physical phenomena and is validated by experiments. The model is Industry 4.0-compliant and can predict weld quality.
JOURNAL OF ADHESION SCIENCE AND TECHNOLOGY
(2023)
Article
Engineering, Manufacturing
Debolina Sen, Surjya K. Pal, Sushanta K. Panda
Summary: A novel strategy involving a concave shoulder tool with three different concavities (3°, 6°, and 9°) and double pass was devised to successfully fabricate longitudinal friction stir welded tubes. Increasing concavity resulted in the formation of flash and thinning of the weld zone due to excessive heat generation caused by enhanced tool contact with tube curvature. The tool with a 3° concavity resulted in negligible pores and excellent weld zone strength, making it suitable for welding tubes using friction stir welding.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
(2023)
Article
Engineering, Manufacturing
Debolina Sen, Bhupesh Singh Katiyar, Sushanta Kumar Panda, Surjya Kanta Pal
Summary: The effect of weld zone on the formability of FSWed AA 5083-O tubes during end expansion was investigated through experiments and finite element simulations. The incorporation of BW fracture model in the FE model predicted the non-linear deformation path and fracture of the weld zone, which was in agreement with experimental results. Microscopic examination revealed void occurrence due to matrix debonding and subsequent fracture of the weld zone. It was concluded that the BW fracture model can aid in tool design and prediction of failure limits during end expansion of welded tubes.
CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Rahul Ajmeria, Mayukh Mondal, Reya Banerjee, Tamesh Halder, Pallav Kumar Deb, Debasish Mishra, Pravanjan Nayak, Sudip Misra, Surjya Kanta Pal, Debashish Chakravarty
Summary: The Industrial Internet of Things (IIoT) and its applications have undergone changes with the introduction of artificial intelligence and machine learning. To overcome the limitations of data-centric techniques, the Brain-Computer Interface (BCI) is proposed as a solution that incorporates human intuition. This study presents a comprehensive examination of the feasibility of utilizing BCI techniques, particularly Electroencephalography (EEG), in industrial applications. The study includes an extensive literature review on EEG basics, signal processing techniques, paradigms, and application scope. Potential use cases, pros and cons, challenges, and solutions are identified. Lab-scale experiments using a single-channel EEG headset demonstrate how this minimalistic setup can enable complex applications in manufacturing processes with an overall accuracy of 70%.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2023)
Article
Computer Science, Hardware & Architecture
Riya Tapwal, Pallav Kumar Deb, Sudip Misra, Surjya Kanta Pal
Summary: In this work, the authors propose Shadows, a virtual blockchain for achieving parallel consensus and efficient data management in industries. By virtualizing the nodes of the blockchain network and creating different blockchains for various activities, Shadows achieves resource-efficient real-time consensus. Through experiments, Shadows is shown to efficiently utilize resources, achieve real-time consensus, provide better data access, and balance the system load using smart contracts.
IEEE TRANSACTIONS ON COMPUTERS
(2023)
Article
Materials Science, Multidisciplinary
Omkar Mypati, Polkampally Pavan Kumar, Surjya Kanta Pal, Prakash Srirangam
Summary: This study compares friction-stir spot welds (FSSW) of pure Al to Cu, with and without graphene interlayer (GL), and analyzes the impact of the interlayer on the mechanical and electrical performance of the weld joint. The results show that the absence of a graphene interlayer leads to the formation of brittle intermetallic compounds (IMCs) at the weld interface, while the presence of the interlayer suppresses the formation of IMCs and enhances the strength of the weld joint. Thinner and high-density twins are observed in the samples with the interlayer, and they contribute to increased tensile load and electrical conductivity.
Proceedings Paper
Telecommunications
Riya Tapwal, Sudip Misra, Surjya Kanta Pal
Summary: In this paper, a solution called CartelChain is proposed for secure communication and optimal throughput of blockchains. The method utilizes smart contracts for data exchange among different blockchains and uses encryption and access control mechanisms for secure and reliable communication. Experimental results show that the method can improve resource utilization, reduce energy consumption, and achieve interoperability among multiple chains.
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022)
(2022)
Proceedings Paper
Materials Science, Multidisciplinary
Abhijit Datta, Ankit Shrivastava, Shitanshu Shekhar Chakraborty, Surjya Kanta Pal
Summary: The effect of welding speed on the strength and ductility of friction stir butt welded assemblies was investigated. The results showed that the ultimate tensile strength and percentage elongation at break of the weld metals decreased with the increase of welding speed.
MATERIALS TODAY-PROCEEDINGS
(2022)
Proceedings Paper
Materials Science, Multidisciplinary
Ankit Shrivastava, Shitanshu Shekhar Chakraborty, Surjya Kanta Pal
Summary: Inconel-625 is known for its excellent strength, corrosion, and creep resistance, making it a suitable material for cladding parts with inferior properties. Laser cladding provides precise metallurgical bonding between the deposited layer and substrate, but challenges such as cracking, delamination, and residual stress can occur during the process.
MATERIALS TODAY-PROCEEDINGS
(2022)